/ Models

Language models

NVIDIA: Nemotron Nano 12B 2 VL (free)

NVIDIA Nemotron Nano 2 VL is a 12-billion-parameter open multimodal reasoning model designed for video understanding and document intelligence. It introduces a hybrid Transformer-Mamba architecture, combining transformer-level accuracy with Mamba’s...

Maker
Nvidia
Context window
128K
Max output
128K
Input / 1M
free
Output / 1M
free
1M in + 1M out
free

Everything else

Max output128K
Input / 1Mfree
Output / 1Mfree
Cache read / 1M
Cache write / 1M
1M in + 1M outfree
Takesimage, text, video
Returnstext
Toolsyes
Reasoningoptional
Open weightsyes
Released2025-10-28
Knowledge cutoff
Retires
Catalog idnvidia/nemotron-nano-12b-v2-vl:free

Using it

In 00, this model is picked per agent — and per tier, so the model that answers your customers need not be the one that writes your code. Get 00.

← all models